The Right to be Forgotten in Pruning: Unveil Machine Unlearning on Sparse Models
This work addresses the right to be forgotten for users of sparse machine learning models, but it is incremental as it builds on existing unlearning algorithms.
The paper tackles the problem of machine unlearning in sparse models by introducing 'un-pruning' to eliminate the impact of deleted data on pruned topologies, and it finds that Membership Inference Attack accuracy is unreliable for evaluation, proposing new metrics instead.
Machine unlearning aims to efficiently eliminate the memory about deleted data from trained models and address the right to be forgotten. Despite the success of existing unlearning algorithms, unlearning in sparse models has not yet been well studied. In this paper, we empirically find that the deleted data has an impact on the pruned topology in a sparse model. Motivated by the observation and the right to be forgotten, we define a new terminology ``un-pruning" to eliminate the impact of deleted data on model pruning. Then we propose an un-pruning algorithm to approximate the pruned topology driven by retained data. We remark that any existing unlearning algorithm can be integrated with the proposed un-pruning workflow and the error of un-pruning is upper-bounded in theory. Also, our un-pruning algorithm can be applied to both structured sparse models and unstructured sparse models. In the experiment, we further find that Membership Inference Attack (MIA) accuracy is unreliable for assessing whether a model has forgotten deleted data, as a small change in the amount of deleted data can produce arbitrary MIA results. Accordingly, we devise new performance metrics for sparse models to evaluate the success of un-pruning. Lastly, we conduct extensive experiments to verify the efficacy of un-pruning with various pruning methods and unlearning algorithms. Our code is released at https://anonymous.4open.science/r/UnlearningSparseModels-FBC5/.